Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3331 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4428. Min Range: -6.4428
Max Act: 6.4428. Min Act: -0.1700
Data Index: 5522733 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4428. Min Range: -6.4428
Max Act: 6.4115. Min Act: -0.1700
Data Index: 1075367 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4428. Min Range: -6.4428
Max Act: 6.3490. Min Act: -0.1700
Data Index: 6628891 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4428. Min Range: -6.4428
Max Act: 6.2240. Min Act: -0.1700
Data Index: 629067 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4428. Min Range: -6.4428
Max Act: 6.0365. Min Act: -0.1700
Data Index: 284535 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.9428. Min Act: -0.1700
Data Index: 7716341 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.9115. Min Act: -0.1700
Data Index: 739901 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.8803. Min Act: -0.1700
Data Index: 8124518 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.8178. Min Act: -0.1700
Data Index: 7840223 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.7553. Min Act: -0.1700
Data Index: 3758012 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.7865. Min Act: -0.1700
Data Index: 7045273 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.7865. Min Act: -0.1700
Data Index: 8540615 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.7553. Min Act: -0.1700
Data Index: 624473 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.7553. Min Act: -0.1700
Data Index: 6476088 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.7553. Min Act: -0.1700
Data Index: 1620266 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.7553. Min Act: -0.1700
Data Index: 8378934 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.7865. Min Act: -0.1700
Data Index: 400194 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.6928. Min Act: -0.1700
Data Index: 5929207 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.6928. Min Act: -0.1700
Data Index: 4877353 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.7240. Min Act: -0.1700
Data Index: 3658643 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19